Reinforcement Learning-Based Slice Isolation Against DDoS Attacks in Beyond 5G Networks

被引:15
作者
Javadpour, Amir [1 ]
Ja'fari, Forough [1 ,2 ]
Taleb, Tarik [1 ]
Benzaid, Chafika [1 ]
机构
[1] Univ Oulu, Fac Informat Technol & Elect Engn, FI-90570 Oulu, Finland
[2] Sharif Univ Technol, Dept Comp Engn, Tehran 1136511155, Iran
来源
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT | 2023年 / 20卷 / 03期
基金
欧盟地平线“2020”; 芬兰科学院;
关键词
5G networks; slice isolation; reinforcement learning (RL); distributed denial of service (DDoS); EMBEDDING ALGORITHM;
D O I
10.1109/TNSM.2023.3254581
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Network slicing in 5G networks can be modeled as a Virtual Network Embedding (VNE) problem, wherein the slice requests must be efficiently mapped on the core network. This process faces two major challenges: covering the maximum number of requests and providing slice isolation. Slice isolation is a mechanism for protecting the slices against Distributed Denial of Service (DDoS) attacks. To overcome these two challenges, we have proposed a novel actor-critic Reinforcement Learning (RL) model, called Slice Isolation-based Reinforcement Learning (SIRL), using five optimal graph features to create the problem environment, the form of which is changed based on a ranking scheme. The ranking procedure reduces the dimension of the features and improves learning performance. We evaluated SIRL by comparing it against four non-RL and nine state-of-the-art RL models. The average results show that the ratio of the covered requests and the damage caused by a DDoS attack of SIRL is 54% higher and 23% lower than that of the other models, respectively. It also has an acceptable learning performance and generality, regarding the reported results that show SIRL agents trained and tested with different networks outperform the other agents by 97%.
引用
收藏
页码:3930 / 3946
页数:17
相关论文
共 30 条
[1]   A novel evaluation function for higher acceptance rates and more profitable metaheuristic-based online virtual network embedding [J].
Aguilar-Fuster, Christian ;
Rubio-Loyola, Javier .
COMPUTER NETWORKS, 2021, 195
[2]  
Asghari A., J. Ambient Intell. Humanized Comput.
[3]   Slice as an Evolutionary Service: Genetic Optimization for Inter-Slice Res me Management in 5G Networks [J].
Bin Han ;
Ji Lianghai ;
Schotten, Hans D. .
IEEE ACCESS, 2018, 6 :33137-33147
[4]   Location Aware and Node Ranking Value-Assisted Embedding Algorithm for One-Stage Embedding in Multiple Distributed Virtual Network Embedding [J].
Cao, Haotong ;
Guo, Yongan ;
Hu, Yue ;
Wu, Shengchen ;
Zhu, Hongbo ;
Yang, Longxiang .
IEEE ACCESS, 2018, 6 :78425-78436
[5]   Novel Node-Ranking Approach and Multiple Topology Attributes-Based Embedding Algorithm for Single-Domain Virtual Network Embedding [J].
Cao, Haotong ;
Yang, Longxiang ;
Zhu, Hongbo .
IEEE INTERNET OF THINGS JOURNAL, 2018, 5 (01) :108-120
[6]  
Dolati M, 2019, IEEE CONF COMPUT, P879, DOI [10.1109/infcomw.2019.8845171, 10.1109/INFCOMW.2019.8845171]
[7]  
Haotong Cao, 2021, IEEE Communications Standards Magazine, V5, P20, DOI [10.1109/mcomstd.001.2000026, 10.1109/MCOMSTD.001.2000026]
[8]  
Hashmi A., 2020, P 11 INT C COMP COMM, P1
[9]  
Jiang P., 2021, QoS-Aware Virtual Network Embedding, P61
[10]  
Lei Zhuang, 2018, MATEC Web of Conferences, V232, DOI [10.1051/matecconf/201823201019, 10.1051/matecconf/201823201019]